← All courses

EDGE FDE

Intermediate

PyTorch to Core AI in Xcode

On a Mac, train a small clothing model on Fashion-MNIST. Use MPS if you have it, or CPU if you do not. Convert it to .aimodel, then show the top label in a SwiftUI app with Core AI.

This course is for you if you can write Python and Swift, and you are new to Core AI.

Lessons

  1. The clothing classifier pipeline
  2. Train ClothingCNN on Fashion-MNIST
  3. Convert ClothingCNN with coreai-torch
  4. Add the clothing model to Xcode
  5. Build a SwiftUI clothing classifier
  6. Profile the clothing inference path
  7. Evaluate the clothing classifier
  8. Fashion-MNIST end-to-end checklist

Key concepts

Takeaways

Agent briefs

Related courses

PyTorch to Android with LiteRT · From the metal to the model · Model architectures in plain English · Diffusion LoRA to Core AI on device